​
Creating a new Document

Once you have access to the Logic dashboard, you can create a new document using the AutoDoc feature or manually. This guide will walk you through both methods.
Want to learn more about how documents work in Logic? Check out the Understanding Documents section.
autodoc

​
Step 1: Access the Logic dashboard

Open the Logic dashboard and log in to your account. Start by clicking the New Document button in the top right corner of the Logic dashboard. This will open a new document editor where you can start building your document.

​
Next, you can choose to create a document using AutoDoc or manually:

Creating a document with AutoDoc is the recommended way to get started, as it automates much of the process. However, if you prefer to create a document manually, you can do that as well. You can edit either document type after creation to better fit your needs. Using AutoDoc is the easiest way to create a document in Logic. It allows you to quickly generate a document based on a simple description of the task you want the Logic API to perform.

​
Step 2: Write a document with AutoDoc

What do you need the Logic API to do? Write a short description of the task you want to accomplish. Once you’ve written your description, you can use the AutoDoc feature to automatically generate a document based on that description. In the example of an image analysis document, the description might be: 
Take an image and tell me what's in it
Once you’ve written your description, click the Create with AutoDoc button. From this description, Logic created a document with the following structure: 
Analyze Image Contents

Introduction
This document provides a step-by-step guide for analyzing an image to describe its contents. The goal is to use image recognition techniques to identify objects, scenes, and activities within the image.

Process

Step 1: Image Preprocessing
1. Obtain the image in a suitable digital format.
2. Ensure the image is clear and of sufficient quality for analysis.

Step 2: Object Detection
1. Apply object detection algorithms to identify objects within the image.
2. Note the types of objects detected (e.g., animals, vehicles, buildings).

Step 3: Scene Understanding
1. Analyze the context and setting of the image.
2. Identify the scene type (e.g., outdoor, indoor, landscape, portrait).

Step 4: Activity Recognition
1. If applicable, recognize any activities or actions depicted in the image.
2. Describe the activities in detail (e.g., walking, running, reading).

Input
- Digital image file.

Output
- Description of the image contents, including:
  - Identified objects
  - Scene type
  - Recognized activities
With this, your document is ready to go. You can jump straight to finishing your document to learn more about setting a title and testing it out.

​
Option 2: Create a Doc Manually

Creating a document manually allows you to have full control over the structure and content of your document. This is useful if you have specific requirements or if you want to create a document that is not easily generated by AutoDoc.

​
Step 2: Write your document manually

What do you need the Logic API to do? Write a description of the task you want to accomplish. In the example of an image analysis document, the description might be: 
"Accept an image as a URL or base64-encoded data and tell me what it is.

Include items like:
- How many people are in it?
- What is the dominant color of the image?
- What's the general mood it invokes?
- What is the gender and or age of the person in the photo?"
To provide the Logic API with context, you can also include examples of input and output. Using the document editor, you can use text formatting to make your document more readable. For example, you can use bullet points to list the items you want the Logic API to include in its analysis. You can also use headings to separate different sections of your document. For example, you might have a section for the input and a section for the output.

​
Step 2B: Optionally, improve your document

If you wrote your document manually, you can improve it by adding more specific details about the image analysis process or including examples of input and output.
If you want to learn more about what makes a good document, check out the What Makes a Good Document? section.
Learn more about how to edit your document in the Editing a Document section.

​
Finish Your Document

document-list-hover-menu

​
Step 3: Set a title

The title is something for you to use to refer to your document later, so choose something descriptive. 
Image Analysis and Description
Locate the document you want to delete in the list of documents on the dashboard. Hover over the document name and click the pencil icon (✏️) to edit the title.

​
Step 4: Test it out!

Once you have created your document, you can test it out using automatically generated test cases. This will help you ensure that it behaves as expected and meets your requirements. To learn more about how to test your document, check out the Testing Documents section.